MindsHub
Star — Console Download

Pricing

Free to start. Pay for what you run.

No subscription either way.

Free

$0

  • MindsHub Air, 5M tokens a month Our alias for the model with the best balance of performance and cost
  • Or bring your own API keys Any model — you pay that provider, not us
  • Share your work Publish an artifact in one click and send the link
  • macOS and Windows
  • Community support Ask the team and other users in the Discord
Download free
No subscription

Pro

Pay as you go at the rates below — no minimum, nothing to cancel

  • Every model, run by us The full catalog through the Model Router — no provider accounts
  • Access management Decide who can open each artifact, and share it privately across your team
  • Automatic failover If a provider goes down, your work moves to the next model
  • Top-ups you control Add credit when you want, or turn on auto-recharge with a cap on how much it can charge each month
  • Support tickets Open a ticket with the team and get a tracked reply
Get started
Rate card

What each model costs on Pro.

Per model, through the MindsHub Model Router. Expand a row for its full billing rules.

Model Provider Input Output Cached input Cache write
Best balance of performance and cost, always current Free tier: the first 5M tokens each month are on us MindsHub $0.20 $1.20 $0.02 $0.25
Free allowance
5M tokens a month at no charge, on either tier. The rates here apply beyond the allowance.
Long prompts — 272K+ tokens
$0.40 input $1.80 output $0.04 cached input $0.50 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way MindsHub bills it.
Web search
$7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately.
Failover order
Gemini 3.6 Flash Tried in this order if MindsHub Air is unavailable, so your work keeps moving.
Balanced everyday workhorse Anthropic $2.00 $10.00 $0.20 $2.50
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$10.00 per 1,000 searches Anthropic's own search, built into the model.
Reasoning effort
lowmediumhighmax Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate.
Failover order
GPT 5.6 Sol Tried in this order if Claude Sonnet 5 is unavailable, so your work keeps moving.
Top-ranked for agentic coding and long projects Anthropic $5.00 $25.00 $0.50 $6.25
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$10.00 per 1,000 searches Anthropic's own search, built into the model.
Reasoning effort
lowmediumhighxhighmax Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate.
Failover order
GPT 5.6 Sol Tried in this order if Claude Opus 5 is unavailable, so your work keeps moving.
Anthropic's top tier for the hardest problems Anthropic $10.00 $50.00 $1.00 $12.50
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$10.00 per 1,000 searches Anthropic's own search, built into the model.
Reasoning effort
lowmediumhighxhighmax Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate.
Failover order
GPT 5.6 Sol Tried in this order if Claude Fable 5 is unavailable, so your work keeps moving.
Fastest Claude, for high-volume simple work Anthropic $1.00 $5.00 $0.10 $1.25
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$10.00 per 1,000 searches Anthropic's own search, built into the model.
Failover order
Gemini 3.6 Flash DeepSeek V4 Pro Tried in this order if Claude Haiku 4.5 is unavailable, so your work keeps moving.
Flagship all-rounder, joint #1 for coding agents OpenAI $5.00 $30.00 $0.50 $6.25
Long prompts — 272K+ tokens
$10.00 input $45.00 output $1.00 cached input $12.50 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way OpenAI bills it.
Web search
$10.00 per 1,000 searches OpenAI's own search, built into the model.
Failover order
No backup configured for this model.
Balanced mid-tier for everyday work OpenAI $2.00 $12.00 $0.20 $2.50
Long prompts — 272K+ tokens
$4.00 input $18.00 output $0.40 cached input $5.00 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way OpenAI bills it.
Web search
$10.00 per 1,000 searches OpenAI's own search, built into the model.
Failover order
No backup configured for this model.
Fast and cheap for high-volume work OpenAI $0.20 $1.20 $0.02 $0.25
Long prompts — 272K+ tokens
$0.40 input $1.80 output $0.04 cached input $0.50 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way OpenAI bills it.
Web search
$10.00 per 1,000 searches OpenAI's own search, built into the model.
Failover order
No backup configured for this model.
Coding specialist for repo-scale changes OpenAI $1.75 $14.00 $0.18 $1.75
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$10.00 per 1,000 searches OpenAI's own search, built into the model.
Reasoning effort
lowmediumhighxhigh Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate.
Failover order
Claude Sonnet 5 Tried in this order if GPT 5.3 Codex is unavailable, so your work keeps moving.
Small and cheap for routine automation OpenAI $0.75 $4.50 $0.08 $0.75
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$10.00 per 1,000 searches OpenAI's own search, built into the model.
Reasoning effort
nonelowmediumhighxhigh Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate.
Failover order
Gemini 3.6 Flash Claude Haiku 4.5 Tried in this order if GPT 5.4 Mini is unavailable, so your work keeps moving.
Cheapest and fastest, for bulk simple tasks OpenAI $0.20 $1.25 $0.02 $0.20
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$10.00 per 1,000 searches OpenAI's own search, built into the model.
Reasoning effort
nonelowmediumhighxhigh Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate.
Failover order
Gemini 3.6 Flash Tried in this order if GPT 5.4 Nano is unavailable, so your work keeps moving.
Huge documents, images, audio and video Google $2.00 $12.00 $0.20 Free
Long prompts — 200K+ tokens
$4.00 input $18.00 output $0.40 cached input Per 1M tokens. Once a prompt crosses 200K tokens, these rates replace the standard ones for the whole request — the same way Google bills it.
Web search
$14.00 per 1,000 searches Google's own search, built into the model.
Cache writes
Free on this model — you're billed only when cached content is read back, at the cached-input rate above.
Failover order
Claude Sonnet 5 GPT 5.6 Sol Tried in this order if Gemini 3.1 Pro Preview is unavailable, so your work keeps moving.
Fast, high-volume everyday tasks Google $1.50 $7.50 $0.15 Free
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$14.00 per 1,000 searches Google's own search, built into the model.
Cache writes
Free on this model — you're billed only when cached content is read back, at the cached-input rate above.
Failover order
GPT 5.4 Mini DeepSeek V4 Pro Tried in this order if Gemini 3.6 Flash is unavailable, so your work keeps moving.
Frontier-class agentic coding and long autonomous runs Moonshot AI $3.00 $15.00 $0.30 Free
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately.
Cache writes
Free on this model — you're billed only when cached content is read back, at the cached-input rate above.
Failover order
DeepSeek V4 Pro Tried in this order if Kimi K3 is unavailable, so your work keeps moving.
Near-frontier reasoning and coding on a budget Fireworks AI $1.74 $3.48 $0.15 $1.74
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately.
Reasoning effort
nonelowmediumhighxhighmax Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate.
Failover order
Kimi K3 Tried in this order if DeepSeek V4 Pro is unavailable, so your work keeps moving.
Multilingual work and broad automation Fireworks AI $0.40 $1.60 $0.08 $0.40
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately.
Failover order
DeepSeek V4 Pro Tried in this order if Qwen3.7 Plus is unavailable, so your work keeps moving.
Top downloadable open model, a coding standout Fireworks AI $1.40 $4.40 $0.14 $1.40
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately.
Failover order
DeepSeek V4 Pro Tried in this order if GLM 5.2 is unavailable, so your work keeps moving.
Meta's frontier line, powers Meta AI Meta $1.25 $4.25 $0.15 $1.25
Long prompts
No surcharge — the full context window bills at the standard rates above.
Web search
$7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately.
Failover order
Claude Sonnet 5 Kimi K3 Tried in this order if Muse Spark 1.1 is unavailable, so your work keeps moving.
Real-time info from X and the web xAI $2.00 $6.00 $0.30 $2.00
Long prompts — 200K+ tokens
$4.00 input $12.00 output $0.60 cached input $4.00 cache write Per 1M tokens. Once a prompt crosses 200K tokens, these rates replace the standard ones for the whole request — the same way xAI bills it.
Web search
$5.00 per 1,000 searches xAI's own search, built into the model.
Failover order
Claude Sonnet 5 Kimi K3 Tried in this order if Grok 4.5 is unavailable, so your work keeps moving.

Token prices are USD per 1M tokens; web search and page fetches are USD per 1,000 calls. Cached input is the discounted rate for prompt content the provider already has cached, and cache write is what it costs to put it there. Expand any model for its long-prompt rates, search pricing and failover order. We mirror each provider's own billing rules rather than inventing our own.

FAQ

Common questions.

What is MindsHub?
MindsHub is the unified workspace where open-source models get things done for you — delegate entire projects and collect finished, shareable results.
How much does MindsHub cost?
The app itself is free and neither tier has a subscription fee. On the Free tier you either bring your own provider API keys and pay those providers directly, or run MindsHub Air with the first 5M tokens each month free. Pro is pay as you go at the per-model rates on the pricing page, from a prepaid balance you top up.
How does the Free tier work?
Download MindsHub Cowork for macOS or Windows and sign in — no card needed. Then pick one of two paths: paste in API keys you already have, and Cowork calls those providers directly for any model while you pay the provider; or use MindsHub Air, which includes 5M tokens every month on us. Either way you can publish an artifact in one click and share the link.
What is MindsHub Air?
MindsHub Air is our alias for the model with the best balance of performance and cost — not a fixed model name. Which model it points at can change without notice as better options ship, so you get the current best without changing anything. It is the model the 5M free monthly tokens apply to, and you can keep using it past that at the rates on the pricing page.
What does Pro add?
Four things. The full model catalog — Claude (Anthropic), GPT (OpenAI), Gemini (Google), Grok (xAI), Muse Spark (Meta), Kimi, DeepSeek, Qwen and GLM — served through the MindsHub Model Router, so you hold no provider accounts. Automatic failover if a provider has an outage. Access management for artifacts: decide who can open each one and share it privately across your team. And support tickets: file one at /support and get a tracked reply from the team, rather than asking in the community.
How does Pro billing work?
Usage bills at the published per-model rates against a prepaid balance, and you decide how it gets funded: add credit when you want, or turn on auto-recharge with a cap on how much it can charge each month. There is no monthly fee, no minimum, and nothing to cancel — if you stop topping up you are back on the Free tier. The pricing page lists the rate for every model, including cached input, cache writes, long prompts, and web search.
Do I need API keys or my own provider accounts?
Only if you want them. On Pro every model is served through the Model Router, so you hold no provider accounts at all. On the Free tier you can bring your own API keys and use any model in the catalog, paying your provider directly — or skip keys entirely and use MindsHub Air on its monthly allowance.
Which models are available?
MindsHub Air on the Free tier. Pro adds the Claude family from Anthropic, the GPT family from OpenAI, Gemini from Google, Grok from xAI, Muse Spark from Meta, and open models including Kimi, DeepSeek, Qwen, and GLM. Exact versions move as providers ship releases, so the table on the pricing page is authoritative: it lists every model with its provider, its input and output price per 1M tokens, and its failover order.
What happens when I use up the 5M free tokens?
The allowance refreshes at the start of each month. Until it does, you have two options that cost you nothing extra: bring your own provider API key and keep working on the Free tier, or top up a Pro balance and carry on at the published rates. Every token type counts toward the 5M — input, output, cached reads and cache writes.
Can I see what a task cost?
Yes. Usage is visible in your account, and the rate card on the pricing page shows exactly what each model charges, so you can work out the cost of a task before you run another like it.
How do models stay current?
Models are referenced by family rather than pinned to versions. When a provider ships a new version, the Model Router resolves to it automatically. Most models also have a designated fallback the router switches to if a provider has an outage — the pricing page shows the failover order per model.
Can I run MindsHub myself?
Yes. MindsHub is open source and runs anywhere — your own computer or your VPC — with your own model endpoints and API keys. The tiers on this page cover the hosted MindsHub service at mindshub.ai, where the Model Router manages models for you.
Which open-source agents power MindsHub?
MindsHub Cowork runs on two interchangeable open-source agent harnesses — Anton, the default, and Hermes. Switch between them in a click and keep your workspace, data, and artifacts.

Delegate your first task.

Free with your own API keys, or 5M monthly tokens on MindsHub Air. Top up only when you want the full catalog.

Get started